This page gives an overview of the presentations about the Million Song Dataset at ISMIR 2011. In particular, it gives access to the tutorial (using prezi website, pdf printout and code on github) and the talk (pdf slides).
TUTORIAL (Monday October 24th, 10am - 1pm)
PDF SLIDES (generated from Prezi)
Code for demonstrations
TALK (Wednesday October the 26th, 4:40pm - 5pm)
Other presentations using the MSD (schedule from the ISMIR program)
- Large-scale music similarity search with spatial trees, B. McFee and G.R.G. Lanckriet, Tuesday 12pm - 1:50pm
- Improving perceptual tempo estimation with crowd-sourced annotations
M. Levy, Wednesday 9:20am-9:40am - The natural language of playlists, B. McFee and G.R.G. Lanckriet, Wednesday 2:50pm - 4:30pm, (Best Poster Award)
- Information Retrieval Meta-Evaluation: challenges and opportunities in the music domain, J. Urbano, Thursday 5:40pm-6pm (slides)
- Audio-based Music Classification with a pretrained convolutional network, S. Dieleman, P. Brakel and B. Schrauwen, Thursday 3:10pm-5pm
- Million Song Dataset integration into the clubmixer framework, A. Schindler, Friday 10am-11:50am